© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31038
    Prev
    Next
    INDEX
    Explanations

    try your potting skills

    np_acts-logits-general · gemini-2.5-flash-lite

    color, music, or composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distress
    0.48
    -
    0.45
    افت
    0.42
     Zone
    0.42
    楨
    0.42
    ändler
    0.41
     tends
    0.40
    寿命
    0.40
    ंकडून
    0.40
     fís
    0.40
    POSITIVE LOGITS
     轻
    0.56
    ிய
    0.51
    ierte
    0.50
    iksaan
    0.50
    ཌ
    0.50
     merhabalar
    0.49
    ஹ
    0.48
     caballo
    0.48
     उपयोगकर्ताओं
    0.47
    WordArray
    0.47
    Activations Density 0.000%

    No Known Activations